图中的忒修斯：迈向可追踪的多跳图导航
Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation
- National Yang Ming Chiao Tung University（国立阳明交通大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对多跳知识图谱问答中推理路径不可见的问题，提出THESEUS框架，将任务重构为图导航，并扩充数据集、设计评估协议、改造现有智能体，使答案伴随可验证的显式推理路径。
AI中文摘要：
多跳知识图谱问答（KGQA）任务要求模型沿着知识图谱中的路径组合关系证据来回答自然语言问题。然而，现有的KGQA系统通常只关注预测最终答案，而不显式建模或验证中间推理步骤，这使得正确答案是否源于忠实的多跳推理变得模糊不清。为解决这一局限，我们将多跳KGQA重新构建为一个问题条件化的图导航问题。我们将这一形式化称为THESEUS——统一语义中的可追踪逐跳证据搜索。在此设定中，智能体接收知识图谱、一个问题和一个主题实体，并遍历一系列关系以到达答案，从而使推理路径显式化。为系统研究这一形式化，我们提供了三项关键贡献。（i）我们将现有的KINSHIP和MQuAKE资源扩充为导航就绪的KGQA数据集，并附有标注的证据路径和改写的问题。（ii）我们设计了评估协议，以衡量路径保真度、对语言变化的鲁棒性，以及跨多跳和多答案问题的性能。（iii）我们将基于路径的成熟知识图谱补全智能体——MINERVA、MultiHopKG和SQUIRE——调整为操作完整的问题嵌入而非符号化的单关系查询，从而使其轨迹能够由自然语言语义引导。这些贡献共同推动KGQA研究朝着可追踪性为基础的系统发展：答案伴随显式推理路径，这些路径与参考证据的一致性可以被系统评估。
英文摘要：
Multi-Hop Knowledge Graph Question Answering (KGQA) tasks require models to assemble relational evidence along paths in a KG to answer natural-language questions. However, existing KGQA systems typically focus on predicting the final answer without explicitly modeling or validating the intermediate reasoning steps, obscuring whether the correct answers arise from faithful multi-hop reasoning. To address this limitation, we re-frame multi-hop KGQA as a question-conditioned graph navigation problem. We refer to this formulation as THESEUS - Traceable Hop-wise Evidence SEarch in a Unified Semantics. In this setting, an agent receives a KG, a question, and a topic entity, and traverses a sequence of relations towards the answer, making the reasoning path explicit. To systematically study this formulation, we provide three key contributions. (i) We augment the existing KINSHIP and MQuAKE resources into navigation-ready KGQA datasets with annotated evidence paths and paraphrased questions. (ii) We design evaluation protocols to measure path fidelity, robustness to linguistic variation, and performance across multi-hop and multi-answer questions. (iii) We adapt established path-based KG completion agents - MINERVA, MultiHopKG, and SQUIRE - to operate on full question embeddings rather than symbolic single-relation queries, enabling their trajectories to be guided by natural-language semantics. Together, these contributions advance KGQA research toward systems where traceability is fundamental: answers are accompanied by explicit reasoning paths whose agreement with reference evidence can be systematically evaluated.
